yt_dlp/extractor/peertv.py

   1 from .common import InfoExtractor
   2 from ..utils import js_to_json
   3
   4
   5 class PeerTVIE(InfoExtractor):
   6     IE_NAME = 'peer.tv'
   7     _VALID_URL = r'https?://(?:www\.)?peer\.tv/(?:de|it|en)/(?P<id>\d+)'
   8     _TESTS = [{
   9         'url': 'https://www.peer.tv/de/841',
  10         'info_dict': {
  11             'id': '841',
  12             'ext': 'mp4',
  13             'title': 'Die Brunnenburg',
  14             'description': 'md5:4395f6142b090338340ab88a3aae24ed',
  15         },
  16     }, {
  17         'url': 'https://www.peer.tv/it/404',
  18         'info_dict': {
  19             'id': '404',
  20             'ext': 'mp4',
  21             'title': 'Cascate di ghiaccio in Val Gardena',
  22             'description': 'md5:e8e5907f236171842674e8090e3577b8',
  23         },
  24     }]
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28         webpage = self._download_webpage(url, video_id)
  29
  30         video_key = self._html_search_regex(r'player\.peer\.tv/js/([a-zA-Z0-9]+)', webpage, 'video key')
  31
  32         js = self._download_webpage(f'https://player.peer.tv/js/{video_key}/', video_id,
  33                                     headers={'Referer': 'https://www.peer.tv/'}, note='Downloading session id')
  34
  35         session_id = self._search_regex(r'["\']session_id["\']:\s*["\']([a-zA-Z0-9]+)["\']', js, 'session id')
  36
  37         player_webpage = self._download_webpage(
  38             f'https://player.peer.tv/jsc/{video_key}/{session_id}?jsr=aHR0cHM6Ly93d3cucGVlci50di9kZS84NDE=&cs=UTF-8&mq=2&ua=0&webm=p&mp4=p&hls=1',
  39             video_id, note='Downloading player webpage')
  40
  41         m3u8_url = self._search_regex(r'["\']playlist_url["\']:\s*(["\'][^"\']+["\'])', player_webpage, 'm3u8 url')
  42         m3u8_url = self._parse_json(m3u8_url, video_id, transform_source=js_to_json)
  43
  44         formats = self._extract_m3u8_formats(m3u8_url, video_id, m3u8_id='hls')
  45
  46         return {
  47             'id': video_id,
  48             'title': self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title').replace('\xa0', ' '),
  49             'formats': formats,
  50             'description': self._html_search_meta(('og:description', 'description'), webpage),
  51             'thumbnail': self._html_search_meta(('og:image', 'image'), webpage),
  52         }